MCP.Market

Nautilus Compass Memory MCP server

online · 75% uptime
by chunxiaoxx·io.github.chunxiaoxx/nautilus-compass·v3.2.0·1.3k stars

Local-first long-term memory for AI agents, with byte-recomputable signed verification receipts.

B82/100grade B
What users say
No reviews yet
Be the first
Safety scan
B82/100

full report

Adoption
Established

1.3k stars56 downloads/wk

Reviews

Write one

Nobody has reviewed Nautilus Compass Memory yet.

If you have run it, two minutes of your experience saves the next person an afternoon.

Nautilus Compass Memory tools

Tool list not cached yet. `describe` through the gateway fetches it live.

Public scan report

scanner v0.1.10 · 2026-10-30 · same rubric, same numbers if you re-run it

1 medium
  • Code scan132 source files scanned20/25
  • Live reliabilityremote reachable in 1477ms (auth required)20/20
  • –Tool poisoningtools not inspected (endpoint requires auth); not countedn/a
  • Auth qualityauth enforced (unknown)9/15
  • Maintenancelast push 0 days ago15/15
  • Maintainer identityregistry namespace matches repository owner6/10

Findings (1)

  • mediumeval / new Function usedexec.eval
    nautilus_compass-3.2.0/daemon.py: … # 砍激活 buffer(可 env 覆盖)。释放显存给共置的 gate B eval(soul 收敛路径)。 try: _max_seq = …
Overall 82/100. Components that don't apply are left out of the denominator. Any critical finding is an F.RubricAppeal a findingJSON

How Nautilus Compass Memory compares

Against every graded MCP server, from our own scans and uptime checks. Updated after each scan run.

Safety score
82/100
higher than 63% of 48,255 servers
Uptime
75%
of our recent checks; the typical remote server answers 100%
Response time
2,343 ms
faster than 4% of 30,031 servers
GitHub stars
1,254
more than 95% of 28,688 servers
Downloads a week
56
more than 46% of 12,191 servers with a package

Install Nautilus Compass Memory in Claude Code, Cursor or VS Code

claude mcp add --transport http nautilus-compass https://compass.nautilus.social/mcp/
Add to Cursor

What the publisher says

From the Nautilus Compass Memory repository's README, as published. We do not edit it. Read it on GitHub

nautilus-compass

<!-- mcp-name: io.github.chunxiaoxx/nautilus-compass -->

Open-source memory & reliability layer for AI agents.

Long-term memory that now beats mem0 on all three LongMemEval-S metrics

while staying fully local & 14× cheaper — plus drift detection and

cross-agent contracts that no other memory layer ships.

Plugin for Claude Code / Desktop · Cline · Cursor · Continue.dev · Zed ·

any MCP client.

Built by Nautilus Platform · open agent ecosystem · join as agent →

🇬🇧 English (this file) · 🇨🇳 中文

What this is (2026-08 state)

Three pillars, one plugin:

1 · Black-box long-term memory — now with SOTA retrieval. Raw text embedded locally with BGE-m3. No extraction LLM at ingest, no graph, no data leaving your machine. In Aug 2026 we added utterance-routed chunk retrieval: single-session and knowledge-update questions route to turn-window chunks (the answer usually lives in ONE user turn; whole-session embedding dilutes it), everything else uses session-level hybrid (BM25 + dense RRF). Result on LongMemEval-S full 500 questions, same-question head-to-head vs mem0 2.0.19 (both sides infer=False, each on its own default embedder — bge-m3 vs vertexai text-embedding-005 — our reproduction):

One-command reproduction (retrieval-only, no LLM calls, CPU works / GPU recommended for the full 500):

bash scripts/reproduce_lmes_retrieval.sh            # full 500
SUBSET=12 bash scripts/reproduce_lmes_retrieval.sh  # smoke

The same utterance ammo overtakes mem0 on its own home benchmark (LOCOMO-10, n=1986: 0.644 / 0.890 vs 0.592 / 0.802) and fixes the single-session collapse on LongMemEval-M (0.20 → 1.00). Full evidence chain with per-type breakdowns and every config flag: docs/evidence/headheadmem0full50020260826.json — including the experiments that failed (cross-encoder reranking hurts* on this corpus; candidate-pool K is a no-op; Qwen3-0.6B swap is a wash).

Shortened. The full README is on GitHub.

Nothing above is checked by us. What we check is on the safety report.

Grade history

  • 2026-10-30restoreC → Bscore 82: eval / new Function used
  • 2026-10-29downgradeB → Cscore 58: Remote endpoint did not respond; eval / new Function used
  • 2026-09-19restoreC → Bscore 82: eval / new Function used

Nautilus Compass Memory: common questions

Is Nautilus Compass Memory MCP server safe?
Mostly: it is graded B (82/100). Read the Nautilus Compass Memory safety report
How do I install Nautilus Compass Memory?
It runs remotely at compass.nautilus.social. Add it to Claude Code, Cursor, VS Code or Claude Desktop with the snippets above, or call it through the mcp.market gateway without installing anything.
Does Nautilus Compass Memory need an API key?
Yes. The registry entry asks for Authorization.
Is Nautilus Compass Memory maintained?
The last commit was 5 days ago (2026-10-30). The latest release is v3.2.0.
Is Nautilus Compass Memory up?
75% of our last 28 checks got an answer. We check remote servers about four times a day.
What can I use instead of Nautilus Compass Memory?
Servers from other publishers that do the same job: Bernstein MCP server and Memorix MCP server.
How does Nautilus Compass Memory compare with other MCP servers?
safety score 82/100 (higher than 63% of 48,255 servers); uptime 75% (of our recent checks; the typical remote server answers 100%); response time 2,343 ms (faster than 4% of 30,031 servers). Full comparison.

Alternatives to Nautilus Compass Memory

Same job from other publishers: the closest match first, then the best rated.

  • Bernstein
    The open-source governance layer for AI agents. Byte-identical run receipts, 40+ adapters, air-gap.
    C
  • Memorix
    Local-first project memory with legacy MCP and 2026 discovery compatibility.
    B